The ClassMarker module's graphical interface is extremely intuitive. This movie shows how easy it is to perform a Train-and-Test analysis.

    Your data, organized into four classes of cells, are shown in an easy-to-understand manner. Mark two of the classes as independent (test) classes, and join each of them with its train class. Then simply click the Train/Test button: ClassMarker finds a set of genes that best discriminate between the two train classes, and runs a cross-validation test. It then uses those genes to classify samples in the test classes, reporting any misclassifications. The discriminant set of genes is displayed for close examination. The results of the classification are shown in a variety of ways, including a 3D view in PCA axes.